<![CDATA[The rapid adoption of online learning environments has generated massive amounts of educational data through Learning Management Systems (LMS). However, one of the major challenges in online education is maintaining and predicting student engagement, which significantly affects learning outcomes and course completion rates. This study proposes a machine learning-based learning analytics approach to predict student engagement in online learning environments. Data are collected from student interaction logs within a Learning Management System, including activity frequency, time spent on learning materials, forum participation, and assessment performance. Several machine learning algorithms, including Random Forest, Support Vector Machine (SVM), and Logistic Regression, are utilized to develop predictive models. The experimental results demonstrate that machine learning models can effectively predict student engagement levels and identify students at risk of disengagement. The findings provide insights for educators and institutions to design adaptive interventions and improve the quality of online learning environments. This research contributes to the growing field of learning analytics by demonstrating how machine learning techniques can enhance engagement prediction and support data-driven decision making in education.]]>
Copyrights © 2025
